Visual question answering improves safety using evidence based agent collaboration
A$^2$Safe: Counterfactual Evidence-Aligned Adaptive Agent Collaboration for Safe and Effective Visual Question Answering
Computer Vision and Pattern Recognition
Summary
Visual Question Answering (VQA) models that understand images and text need to give safe and accurate answers, especially when the question and image together might create risk. The authors propose a new approach called A²Safe that carefully tracks and aligns the evidence in both the image and question to make clear safety decisions. This method adapts how it responds, either directly answering or questioning the evidence when uncertain or risky. Their approach improves safety metrics and reduces unnecessary refusals while keeping overall answer quality high.
What this means in practice
- •For multimodal ai developers: Integrate A²Safe to enhance safety and reliability in systems answering image-based questions by using explicit evidence alignment and adaptive responses.
- •For automated content moderation teams: Use A²Safe framework to better detect and handle risky image-question pairs by grounding safety decisions in detailed evidence analysis.
Authors
Quanxing Xu, Ling Zhou, Xian Zhong, Jinyu Tian, Xiaohua Huang, Rubing Huang, Chia-Wen Lin
Abstract
Visual Question Answering (VQA) with Multimodal Large Language Models (MLLMs) requires not only producing safe and effective responses, but also grounding safety decisions in the multimodal evidence that determines risk. Recent safety-alignment methods improve refusal behavior and contextual risk awareness, yet correct safety outcomes may still rely on superficial textual or visual correlations, particularly when risk emerges from interactions between individually benign image and question content. To address this issue, we propose A$^2$Safe, a counterfactual evidence-aligned adaptive agent collaboration framework for safe and effective VQA. A$^2$Safe organizes localized visual observations, textual intent, and cross-modal risk relations through a Grounded Safety Evidence Board, making the basis of safety decisions explicit. Counterfactual safety evidence alignment enforces invariance to safety-irrelevant changes while requiring appropriate safety-state and response-mode transitions when risk-critical evidence is minimally altered. The resulting evidence state further supports adaptive collaboration, enabling direct answering when grounded evidence is sufficient and invoking policy critique and response revision when evidence is risky, uncertain, or conflicting. Under complementary safety-critical and general VQA protocols, A$^2$Safe achieves a 95.72 SIUO safety score, reduces the benign refusal rate on MOSSBench to 14.67%, and maintains an average general VQA score of 78.34 with 27.8% token overhead. These results support counterfactual evidence-aligned adaptive collaboration for safe and effective multimodal question answering.